Dynamic Recurrent Neural Networks for Control of Unknown Nonlinear Systems

Abstract

A scheme of dynamic recurrent neural networks (DRNNs) is discussed in this paper, which provides the potential for the learning and control of a general class of unknown discrete-time nonlinear systems which are treated as “black boxes” with multi-inputs and multi-outputs (MIMO). A model of the DRNNs is described by a set of nonlinear difference equations, and a suitable analysis for the input-output dynamics of the model is performed to obtain the inverse dynamics. The ability of a DRNN structure to model arbitrary dynamic nonlinear systems is incorporated to approximate the unknown nonlinear input-output relationship using a dynamic back propagation (DBP) learning algorithm. An equivalent control concept is introduced to develop a model based learning control architecture with simultaneous on-line identification and control for unknown nonlinear plants. The potentials of the proposed methods are demonstrated by simulation results.